Office of Research & Development |
|
Informatics, also known as biomedical, clinical, or health care informatics, is a relatively new discipline that has been spurred by the rapid growth of health care technology. In its broadest sense, informatics improves human health, health care, and biomedical research by making health data accessible to researchers and clinicians and using that data to benefit patients. VA informatics research covers several areas, including:
In 2019, VA announced the establishment of the National Artificial Intelligence Institute (NAII). The NAII provides and incorporates AI research and development that is meaningful to Veterans and the American people. AI uses computers to simulate human thinking, especially in applications involving large amounts of data. VA currently uses AI to reduce Veterans’ wait times for care, identify those at high risk for suicide, and help physicians incorporate the results of cancer lab tests and choose effective therapies. The institute will usher in new capabilities and opportunities to improve health outcomes for Veterans and others.
All four services of VA’s Office of Research and Development (ORD) support research in informatics. However, due to the nature of its mission VA’s Health Services Research & Development (HSR&D) Service supports a comprehensive informatics research program, funding intramural research projects and maintaining two resource centers that promote access to clinical and administrative data for VA researchers.
The mission of the VA Informatics and Computing Infrastructure (VINCI) HSR&D resource center is to reduce the time and effort required to appropriately access, properly understand, and effectively use Veteran data for research. To support the mission, VINCI partners with the Office of Information and Technology (OI&T) to deliver a full-service computing environment with access to data, tools, and supporting services. Since thousands of research projects depend on VINCI for success, maintaining a reliable, sustainable infrastructure is key. At the same time, data-driven research and the scientific frontiers opened by new tools and methods constantly push research needs towards modernization. VINCI balances sustainment and modernization by working to optimize processes through simplification and standardization.
VINCI participates in the Observational Health Data Sciences and Informatics (OHDSI, pronounced “Odyssey”) program, an international, interdisciplinary collaborative to maximize the value of health data through large-scale analytics. In 2020, OHDSI began running studies focusing on COVID-19. VINCI has been a valuable collaborator to the OHDSI’s COVID-19 data initiatives in creating predictive models based on historical data and testing them on new COVID-19 data, and using historical data to answer relevant safety questions.
The VA Information Resource Center (VIReC) strives to advance VA’s capacity to use data and information systems effectively and to foster communication between data users and the VA health care community through a range of activities that support research in informatics, outcomes, and effectiveness; health care operations; implementation; and organizational decision-making.
VIReC is a key resource to help researchers navigate VA’s complex data environment. It also plays a significant role in VA’s Electronic Health Record Modernization (EHRM) effort to migrate its EHR to Cerner Millennium.
Code to Catch Cancer
As the largest integrated healthcare system in the nation, the VA has a proud history of innovation regarding the maintenance of medical records. Starting with the Internet's infancy, VA revised and improved the earliest electronic record keeping software for ease of access to VA providers. Today, where research on targeted algorithms works to make sure no Veteran is left behind, the VA is dedicated to harnessing the power of technology for the wellbeing of the Veteran community.
Problem-solving is at the heart of VA research. In the case of Dr. Singh, he solved patient follow-up issues for varying cancer screening results; the solution was an algorithm. Utilizing the most modern technologies available, the VA continues to look out for its Veteran community.
Current areas of VA research in health care informatics include virtual and connected care technologies, EHR modernization research, NLP, phenotype studies, adverse event monitoring, clinical decision support systems, and care management tools.
If you are interested in learning about joining a VA-sponsored clinical trial, visit our research study information page.
VA has been a longstanding early adopter of virtual care technologies to support health care delivery, yet evidence has lagged regarding how best to implement such technologies, their impacts on care, and the associated experiences of Veterans and clinical team members. As VA’s traditional health care structures evolve to include more care in the community and home, little is known about the new needs that will arise from these changes and how they will affect health care processes and outcomes. ORD has funded multiple studies that examine different types of virtual care technologies and also facilitates coordination and collaborations of virtual care research through the Virtual Care Consortium of Research.
Use of VA telehealth services during the COVID-19 pandemic—A study begun in 2020 at the VA Greater Los Angeles Healthcare System (VAGLAHS) by VA’s Veterans Emergency Management Evaluation Center is looking at how telehealth services are being used at three types of outpatient clinics within VAGLAHS (primary, specialty, and home-based primary care) to provide continuity of care to Veterans during the COVID-19 pandemic.
The study hopes to improve understanding of telemedicine capabilities at VAGLAHS clinics, and to learn how telemedicine capabilities at each of the clinics were implemented in response to the crisis.
Wearable monitoring analytics to improve outcomes in heart failure—This VA study will develop an implementation strategy for noninvasive remote monitoring of patients with heart failure, using predictive analytics to generate clinical alerts. The study is funded September 2020 through August 2024.The result will be a reliable link between the clinical alert and an intervention that can affect the clinical outcome of the patient. Algorithmic response to the device alert will be a subject of ongoing validation and updates as part of the learning health care system concept.
This will allow for integration with VA’s EHR, enable optimization and standardization of the response process, and decrease alert fatigue. Furthermore, the researchers will evaluate patient and provider attitudes toward using remote monitoring to guide heart failure therapy, as well as the impact of this approach on key clinical outcomes. Investigators hope to implement remote monitoring into the clinical workflow of heart failure care and conduct a feasibility study of non-invasive remote monitoring in chronic heart failure.
Extending treatment to Veterans with diabetes—Type 2 diabetes is a long-term medical condition in which the body doesn’t use insulin properly, resulting in unusual blood sugar levels. It affects approximately 24% of Veterans who seek care within VA. A study led by researchers at the Edith Nourse Rogers Memorial Veterans Hospital in Bedford, Massachusetts, aims to refine and beta-test a texting protocol for type 2 diabetes called DD-TXT.
Investigators will also conduct a randomized controlled comparison of the protocol to determine whether it is more effective than DSE, which is a diabetes skills education-only texting protocol based on a skills workbook currently given to VA patients with diabetes.
The DD-TXT protocol includes providing Veterans with customizable messages on medication management, blood sugar and blood pressure monitoring, preventive care, problem-solving, appointment reminders, and administrative messages. It also will include a library of modules on topics such as nutrition, physical activity, weight management, emotional coping, and goal-setting to motivate and educate Veterans in their efforts.
Virtual nurse intervention for Veterans with CHF or COPD—VA researchers have developed a computer program designed to simulate a discharge nurse to help Veterans with chronic heart failure (a condition in which the heart has trouble pumping blood through the body) and chronic obstructive pulmonary disease (COPD)—a chronic inflammatory lung disease that causes obstructed airflow from the lungs).
A trial led by a researcher at the Edith Nourse Rogers Memorial Veterans Hospital is testing the new program and aims to guide the program’s implementation throughout the VA health care system and determine the effectiveness and budget impact.
In the program, a computer-generated “nurse” appears on a computer touch screen and educates hospitalized Veterans with CHF or COPD about the important components of transitioning to home care. The virtual nurse also shows them how to send and receive text messages on their mobile phones. Once they are home, the virtual nurse continues to coach them and their family members and improves their access to care through two-way computer-tailored text messages.
CHF and COPD are among the most common reasons for admission and re-admission to VA hospitals, and the transition of these patients from hospital to home places them in jeopardy of adverse events and increases their risk of rehospitalization.
Virtual Care Consortium of Research (CORE)—VA’s Virtual Care CORE works closely with other VA organizations to facilitate seamless integration of virtual care into daily health care practice. The CORE’s goals include facilitating adoption of virtual care in VA; fostering research on the impact of virtual care in VA; and creating a robust, healthy network of virtual-care investigators whose work is aligned with the needs and priorities of other VA programs such as the offices of Connected Care, Rural Health, and Primary Care Services.
Electronic Health Record Modernization (EHRM) Implementation—With the transition to the Cerner system nationally over a 10-year period, VA has an unprecedented opportunity to study how the transition to a new EHR impacts not only traditional health services outcomes such as quality and safety but also organizational or cultural outcomes such as change management and implementation. ORD created the Coordinating Hub to Promote Research Optimizing Veteran-centered EHR Networks (PROVEN) in April 2020. The PROVEN Hub is designed to help ORD research make scientific contributions to EHRM efforts. The PROVEN Hub will:
NLP is a field of study within computer science that uses AI and computational linguistics to interpret and understand written language. It is especially useful to medical researchers who wish to use medical data contained within a Veteran's EHR that was written as free text (rather than being entered into a form with discrete fields).
Improving outcomes in Veterans with heart failure and chronic kidney disease—Heart failure is a major public health problem, with both high mortality and hospital readmission rates. Two medications, angiotensin-converting enzyme inhibitors (ACEIs) and angiotensin receptor blockers (ARBs), improve both issues in heart failure patients—but also adversely affect kidney function and can increase the risk of acute kidney injury, chronic kidney disease (CKD) progression, and kidney failure, especially in high doses.
Using an automated machine-learning algorithm, a team led by a Washington DC VA researcher is developing a risk prediction model designed to maximize clinical benefit and minimize kidney harm to individual Veterans. The team hopes its findings will help clinicians develop a personalized approach to the use of ACEIs and ARBs in patients with heart failure and CKD.
Another study involving CKD, affecting up to 36% of all VA users during FY 2006-2014, is using algorithms to look at the value of different ways to prevent the disease. The four-year study, led by researchers at the Memphis VA Medical Center, hopes to find interventions that might help to prevent the disease in the general VA population, and to decrease mortality and clinical events among Veterans who already have CKD, both in the overall population and among racial minorities.
Measuring, mining, and understanding communication behaviors—Researchers at the Edith Nourse Rogers Memorial Veterans Hospital are using NLP to look at clinicians’ communication behaviors throughout VA. They are mining the secure messaging feature in VA’s MyHealtheVet patient portal to look at ways in which clinicians provide information to their patients and to see if good communication lowers patients’ use of health care services and improves medication adherence. The team hopes to measure communication between Veterans and their health care teams, and create indicators that define positive and negative communication behaviors.
Phenotype studies search for specific traits across populations of patients by using informatics tools and NLP techniques. For many research initiatives, ranging from precision medicine to predictive analytics to population health, extraction of phenotypes from the EHR is a central task. Optimal EHR phenotyping is vital for large-scale research programs underway in VA, including the Million Veteran Program (MVP) and multicenter clinical trials that seek to generate evidence on the effectiveness of various treatments.
The VA Phenomics Library will provide a centralized community resource to store, archive, and share phenotype definitions, data mapping, and other metadata used in VA projects and publications.
The library will improve the reusability and scalability of information across VA projects, enhance collaboration, and serve as a resource for identifying eligible cases for research such as clinical trials or epidemiological studies. Investigators will gain access to already developed phenotypes, be able to identify potential collaborators, and collectively advance phenomics science in the VA research community.
Collecting VA system-wide genetic data—MVP provides a rich platform for discovering the relationships among genes, environmental exposures, and health. As of September 2020, more than 825,000 Veterans have provided DNA specimens, military exposure information, and access to their health records (by authorized researchers) to facilitate studies on topics ranging from the causes of Gulf War illness and posttraumatic stress disorder (PTSD) to functional impairment in schizophrenia and bipolar disorder.
A study led by researchers at the VA Palo Alto Health Care System is using a tool called APHRODITE (Automated Phenotype Routine for Observational Definition, Identification, Training, and Evaluation) to identify established genetic links among MVP participants. APHRODITE uses state-of-the-art machine-learning algorithms to identify individuals with a condition much more quickly than current search methods. If APHRODITE works as well or better than current methods, the team may help maximize the efficiency of genetic discoveries and make it easier to rapidly replicate findings.
Advancing the phenotyping of acute kidney injury for MVP—Acute kidney injury (AKI) is a complex and deadly disease. The most common and severe AKI results in tissue damage to the kidneys and is known as intrinsic AKI (iAKI). Poor understanding of what puts patients at risk for iAKI has prevented the development of effective treatments. An important first step is to understand if there is a genetic basis that explains differences in risk for developing iAKI. Studies in this area have been limited by small sample size and poor phenotyping of iAKI.
The goals of a proposal by researchers from the VA Tennessee Valley Healthcare System in Nashville are to advance the phenotyping of iAKI within MVP using both data-driven and clinically guided approaches. The team will then perform genome-wide association and predicted gene-expression studies for the phenotypes developed. The results will help explain why some patients experience iAKI while others do not, provide some insight into the potential ways that iAKI develops, and generate new hypotheses about how iAKI may be treated and prevented.
Adverse event monitoring (AEM) and reporting is an important part of patient care, research, and clinical trials. Due to the relatively small number of patients typically followed in a clinical trial, adverse events often don't surface until a drug or medical product is in wide commercial use. Success depends in large part on having effective AEM processes and tools available, and communicating those standards to researchers and clinicians.
Monitoring invasive non-surgical procedures—Outpatient procedures in three non-surgical clinical specialties (interventional cardiology, interventional radiology, and gastrointestinal endoscopy) result in more than 50,000 emergency department visits or hospitalizations every year in the U.S. As many as half of these visits can be prevented through improvements to the ways in which those procedures are conducted. A researcher with the VA Boston Health Care System is using VA data on these procedures to develop a database of the kinds of adverse events that occur as a result of these procedures. She also intends to identify the contributing factors that lead to those adverse events, in hopes of improving patient safety and reducing complications.
Optimizing treatment of hepatitis C—Hepatitis C is an infection caused by a virus that attacks the liver and leads to inflammation. It is spread by contact with contaminated blood in ways such as sharing needles or from unsterilized tattoo equipment. New antiviral medications for the illness are highly effective, but are also costly, making it difficult for some health care systems to meet the growing demand for treatment.
Researchers at the VA Ann Arbor Health Care System are developing a risk-based, systematic approach to deciding who should be treated and when, to maximize treatment benefit while limiting clinical and economic harms. To do so, they are using a machine-learning risk prediction model to identify patients at both high and low risk for disease progression. They will also speak to Veterans both with and without chronic hepatitis C to find out their preferences and values regarding risk-based treatment, and will use simulation modeling to estimate the benefit of risk-based treatment.
The team expects to develop a strategy to systematically identify patients at high risk for chronic hepatitis C, so that they can be treated early on in their disease progression. Information gleaned from conversations with Veterans will also help guide policymakers in setting guidelines for treatments with high-cost medications.
Given the vast body of scientific and medical knowledge available to clinicians, it is becoming increasingly important to develop clinical decision support (CDS) tools to help them deliver the best care to Veterans. These tools are also needed for the growing group of older individuals who often experience a host of complex diseases that can occur together—like heart disease and diabetes—and complicate care.
Developing tools for dialysis decision support in older adults—Investigators at the VA Palo Alto Health Care system are generating new tools to help older Veterans with advanced CKD and end-stage renal disease make informed decisions about their future. Every year, more than 25,000 Americans above the age of 75 begin maintenance dialysis treatment.
Although dialysis can prolong life, it requires profound changes in lifestyle, entails substantial risks for complications, and has a high likelihood of permanent disability. Few patients, however, receive information about their prognosis or options to manage their conditions without dialysis. Instead, they believe they have a choice only between dialysis and death.
The research team is comparing survival rates to illustrate trade-offs between dialysis and medical management, developing a web-based risk benefit calculator and decision aid, and evaluating the usability and acceptability of the tools they are developing.
Incorporating Veterans preferences into lung cancer screening decisions—Lung cancer is the leading cause of cancer deaths in the United States. The United States Preventive Services Task Force recommends that people who have smoked for more than 30 years and who continue to smoke, or have quit less than 15 years ago, be screened annually for the disease. There are both benefits (reduction in deaths) and downsides (including false positives, follow-up testing, and overdiagnosis) related to annual screenings, and some Veterans are reluctant to be screened due to those negatives.
Researchers at the Corporal Michael J. Crescenz VA Medical Center in Philadelphia are developing a web-based lung cancer screening decision tool that will help Veterans weigh these benefits and downsides, anticipate their future health, and communicate their values to their health care providers. The researchers are getting patients’ and clinicians’ input, building the tool , and testing its efficacy. The research team believes that while basic educational tools to inform lung cancer decision-making have been developed, they do not incorporate an assessment of patient preferences, which the new tool does.
Using measurement science to standardize VHA data—The primary goal of VA’s Measurement Science QUERI is to integrate measurement science into health care for Veterans. Measurement science (defined as the theory, practice, and application of suitable metrics) is at the core of VA's learning health care system and is a critical component at every stage of quality- improvement and implementation. Using system-wide data to promote performance measurement, improvement efforts, and electronic tools such as clinical reminders depends on the uniformity of those metrics, the efficiency with which they can be obtained, and the accuracy with which they are measured. Whenever a health care decision is made, it must be based on valid and reliable data linked with all relevant information.
Veterans are in particular need of optimal care coordination, given that many suffer from co-occurring health conditions, mental health problems, and a challenging home environment. Poor care coordination is a principal cause of avoidable illness, death, excess resource use, and dissatisfaction among Veterans and their health-care teams.
Improving statin use—A team led by researchers from the Michael E. DeBakey VA Medical Center in Houston is using NLP tools to look at physician notes in VA’s EHR system to determine why statins (drugs that reduce levels of fats, including triglycerides and cholesterol, in the blood) are or are not being prescribed to Veterans; conducting interviews with patients and clinicians; and pilot-testing an intervention to improve optimal statin use in Veterans with cardiovascular disease.
The proper use of statins can reduce cardiovascular disease and heart attacks. Yet many Americans, including Veterans, are not taking statins in an optimal manner. Besides identifying patients who are not receiving the proper doses of statins, the team also hopes to help caregivers identify patients intolerant of statins who may be candidates for other new FDA-approved drugs that have the same effects.
Improved follow-up on test results—Researchers with the Michael E. DeBakey VA Medical Center are developing and evaluating a new program to reduce the number of missed test results at VA facilities. EHRs such as the system VA uses can improve communication processes among clinicians and with Veterans, but there are still vulnerabilities, including the fact that clinicians sometimes fail to follow up on abnormal test results. This failure can result in delays in providing patients with accurate diagnoses of their health care problems.
The team plans to develop strategies, change concepts, and action steps to help health care systems reduce the number of missed results. These tools will help VA identify patients whose test results might have been missed and implement a surveillance and improvement program that will translate into appropriate actions. The program will help VA facilities create back-up systems to monitor delays in diagnoses resulting from missed results.
Teledermatology mobile apps—A study led by researchers at the San Francisco VA Health Care System is testing the hypothesis that successful implementation of two innovative mobile apps for Veterans and dermatologists will make it easier for Veterans to get dermatologic care. The study will also examine the factors that affect the successful implementation and impact of both apps.
One of the two apps is called VA Telederm. The app streamlines the consultative process among primary care providers, teledermatology imagers, and dermatologists to make it easier to use teledermatology in VA primary care clinics. The other app is My Telederm, which allows established VA dermatology patients to follow-up with VA dermatologists remotely instead of requiring in-person clinic-based appointments.
Teledermatology is an area of dermatology that uses telecommunication technologies to capture visual or audio information about skin lesions and then send those data securely to a dermatologist. At VA, teledermatology is an effective option to enhance Veterans’ access to high quality skin care.
Developing innovative methods to analyze health care data for aging Veterans—Older Veterans with multiple chronic diseases are particularly vulnerable to adverse outcomes when transitioning to a different health care provider or facility, especially when that care is complicated by a co-existing mental health or social issue like homelessness or poverty.
A study led by researchers at the James J. Peters VA Medical Center in the Bronx is examining important research questions relating to the health of seriously ill older Veterans and exploring new models of care delivery. The team is looking at different treatments for illnesses affecting these Veterans using propensity scores, which is the probability of a Veteran receiving a particular treatment given a set of observed characteristics. They hope to use the information they obtain to strengthen other researchers’ abilities to use existing data to improve health care value and efficiency for older Veterans.
AI Tech Sprint brings together private industry and innovation to benefit Veterans, Nov. 4, 2020
VA wants to be a leader in using artificial intelligence, Federal News Network, March 2, 2020
Study gauges VA providers’ views on predictive-analytics tool that assesses patient risk, VA Research Currents, Nov. 13, 2019
VA rolls out nationwide software system for research oversight and reporting, VA Research Currents, Oct. 31, 2019
VA national precision oncology program brings tailored cancer treatment to Veterans, VA Research Currents, Oct. 3, 2019
VA-DeepMind partnership reports on technology for early detection of life-threatening kidney condition, VA Research Currents, Aug. 20, 2019
Gene variants tied to kidney disease have only modest cardiovascular effect in African Americans, VA Research Currents, Aug. 16, 2019
MVP study identifies genes linked to re-experiencing symptoms in PTSD, VA Research Currents, July 29, 2019
VA aims to expand artificial-intelligence research, appoints first AI director, VA Research Currents, July 10, 2019
Data-sharing milestone: major DoD study on service member, Veteran health to add VA data, VA Research Currents, Aug. 9, 2018
Electronic alerts lower co-prescribing of opioids and benzodiazepines, VA Research Currents, April 4, 2018
PROVEN: coordinating hub to promote research optimizing Veteran-centric EHR networks
Virtual Care consortium of research (VC CORE)
Investigator Insights: Using Informatics to Identify Veterans At-Risk for Homelessness, Veterans Health Administration Video, Dr. Adi Gundlapalli
Modifying the minimum criteria for diagnosing amnestic MCI to improve prediction of brain atrophy and progression to Alzheimer’s disease. Vuoksimaa E, McEvoy LK, Holland D, Franz CE, Kremen WS; Alzheimer’s Disease Neuroimaging Initiative. Requiring impairment on at least two memory tests for mild cognitive impairment diagnosis can markedly improve prediction of medial temporal atrophy and conversion to Alzheimer’s disease. Brain Imaging Behav. 2020 Jun;14(3):787-796.
Racial differences in patient consent policy preferences for electronic health information exchange. Turvey CL, Klein DM, Nazi KM, Haidary ST, Bouhaddou O, Hsing N, Donahue M. Observed large differences by race and ethnicity in privacy preferences for electronic health information exchange should inform implementation of these programs to ensure cultural sensitivity. J Am Med Inform Assoc. 2020 May 1;27(5):717-725.
Continuous wearable monitoring analytics predict heart failure hospitalization: the LINK-HF multicenter study. Stehlik J, Schamalfuss C, Bozkurt B, Nativi-Nicolau J, Wholfahrt P, Wegerich S, Rose K, Ray R, Schofield R, Deswal A, Sekaric J, Anand S, Richards D, Hanson H, Pipke M, Pham M. A wearable sensor can provide accurate early detection of impending rehospitalization from heart failure with a predictive accuracy comparable to implanted devices. Circ Heart Fail. 2020 Mar;13(3):e006513.
Comparing artificial intelligence platforms for histopathologic cancer diagnosis. Borkowski AA, Wilson CP, Borkowski SA, Thomas LB, Deland LA, Grewe SJ, Mastorides SM. Two machine learning platforms were successfully used to provide diagnostic guidance in the differentiation between common cancer conditions in Veteran populations. Fed Pract. 2019 Oct;36(10):456-463.
Association of APOL1 risk alleles with cardiovascular disease in blacks in the Million Veteran Program. Bick AG et al. In 31,000 African American Veterans, gene variants associated with chronic kidney disease have only a modest link to cardiovascular disease. Circulation. 2019 Sep 17;140(12):1031-1040.
Genome-wide association study of post-traumatic stress disorder reexperiencing symptoms in >165,000 US Veterans. Gelernter J, Sun N, Polimanti R, Pitrzak R, Levey DF, Bryois J, Lu Q, Hu Y, Li B, Radhakrishnan K, Aslan M, Cheung KH, Li Y, Rajeevan N, Sayward F, Harrington K, Chen Q, Cho K, Pyarajan S, Sullivan PF, Quaden R, Shi Y, Hunter-Zinck H, Gaziano JM, Concato J, Zhao H, Stein MB; VA Cooperative Studies Program (#575B) and the Million Veteran Program. Multiple locations in the human genome are related to the risk of re-experiencing traumatic memories. Nat Neurosci. 2019 Sep;22(9):1394-1401.
Genome-wide association study of peripheral artery disease in the Million Veteran Program. Klarin D et al. Identification of 19 genetic markers most responsible for causing peripheral artery disease should lay the groundwork to develop new approaches towards treating the disease. Nat Med. 2019 Aug;25(8):1274-1279.
Using predictive analytics to guide patient care and research in a national health system. Nelson KM, Chang ET, Zulman DM, Rubenstein LV, Kirkland FD, Fihn SD. Among VA clinicians who used the department’s Care Assessment Needs report, most believed the score accurately identified their high-risk patients, and used the score regularly. J Gen Intern Med. 2019 Aug;34(8):1379-1380.
A clinically applicable approach to continuous prediction of future acute kidney injury. Tomasev N et al. A deep learning approach for the continuous risk prediction of future kidney deterioration in patients may offer opportunities for identifying patients at risk within a time window that enables early treatment. Nature. 2019 Aug;572(7767):116-119.
Regional data exchange to improve care for veterans after non-VA hospitalization: a randomized controlled trial. Dixon BE, Schwartzkopf AL, Guerrero VM, May J, Koufacos NS, Bean AM, Penrod JD, Schubert CC, Boockvar KS. The article describes a clinical trial to examine the effectiveness of event notification on health outcomes for older adults who experience acute care events and compare approaches to how providers respond to event notifications. BMC Med Inform Decis Mak. 2019 July 4;19(1):125.
Descriptive usability study of CirrODS: clinical decision and workflow support tool for management of patients with cirrhosis. Garvin JH, Ducom J, Matheny M, Miller A, Westerman D, Reale C, Slagle J, Kelly N, Beebe R, Koola J, Groessl EJ, Patterson ES, Weinger M, Perkins AM, Ho SB. A novel web-based combined clinical decision-making and workflow support tool to alert and assist clinicians caring for patients with cirrhosis was developed. JMIR Medical Inform. 2019 July 3;7(3):e13627.
Test results management and distributed cognition in electronic health record-enabled primary care. Smith MW, Hughes AM, Brown C, Russo E, Giardina TD, Mehta P, Singh H. Managing abnormal test results in primary care involves coordination across various settings. Health information technology should address the risks of distributed work by supporting awareness of team and task status for reliable management of results. Health Informatics J. 2019;25(4):1549-1562.
End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography. Ardilla D, Kiraly AP, Bharadwaj S, Choi B, Reicher JJ, Peng L, Tse D, Etemadi M, Ye W, Corrado G, Naidich DP, Shetty S. Deep learning models can increase the accuracy, consistency, and adoption of lung cancer screening worldwide. Nat Med. 2019 Jun;25(6):954-961.
Validation of an electronic medical record-based algorithm for identifying posttraumatic stress disorder in U.S. Veterans. Harrington KM, Quaden R, Stein MB, Honerlaw JP, Cissell S, Pietrzak RH, Zhao H, Radhakrishnan K, Aslan M, Gaziano JM, Concato J, Gagnon DR, Gelernter J, Cho K; VA Million Veteran Program and Cooperative Studies Program. An algorithm to identify PTSD in electronic health records has high accuracy when compared with manual chart review. J Trauma Stress. 2019 Apr;32(2):226-237.
Improving electronic health record note comprehension with NoteAid: randomized trial of electronic health record note comprehension interventions with crowdsourced workers. Lalor JP, Woolf B, Yu H. Use of a freely available web-based tool led to better patient understanding of medical notes within their electronic health records. J Med Internet Res. 2019 Jan 16;21(1):e10793.
Machine learning models to predict disease progression among veterans with hepatitis C virus. Konerman MA, Beste LA, Van T, Liu B, Zhang X, Zhu J, Saini SD, Su GL, Nallamothu BK, Ioannou GN, Waljee AK. Boosted-survival-tree based models using longitudinal information are statistically superior to cross-sectional or linear models for predicting development of cirrhosis in chronic hepatitis C virus, though all four models were highly accurate. PloS One. 2019;14(1):e0208141.
Dialysis versus medical management at different stages and levels of kidney function in Veterans with advanced CKD. Tamura MK, Desai M, Kapphahn KI, Thomas IC, Asch SM, Chertow GM. Providing dialysis at higher levels of kidney function may extend survival for some older patients. J Am Soc Nephrol. 2018 Aug;29(8):2169-77.
Electronic medical record alert associated with reduced opioid and benzodiazepine coprescribing in high-risk Veteran patients. Malte CA, Berger D, Saxon AJ, Hagedorn HJ, Achtmeyer CE, Mariano AJ, Hawkins EJ. Medication alerts hold promise as a means of reducing opioid and benzodiazepine coprescribing among certain high-risk groups. Med Care. 2018 Feb;56(2):171-178.
Development of a natural language processing engine to generate bladder cancer pathology data for health services research. Schroek FR, Patterson OV, Alba PR, Pattison EA, Seigne JD, Duval SL, Robertson DJ, Sirovich B, Goodney PP. Natural language processing was successful at identifying details on patients with bladder cancer from medical reports. Urology. 2017 Dec;110;84-91.
Electronic health record alert-related workload as predictor of burnout in primary care providers. Gregory ME, Russo E, Singh H. Increased notifications from electronic health records can contribute to provider burnout. Appl Clin Inform. 2017 Jul 5;8(3):686-697.
Download PDF
AI to Maximize Treatment for Veterans with Head and Neck Cancer
VA Further Develops Its Central Biorepository: VA SHIELD
VA Launches Scott Hannon Initiative for Precision Mental Health
Can an Algorithm Prevent Suicide?, The New York Times, Nov. 23, 2020
Hydroxychloroquine ineffective for COVID-19, VA study suggests, Medicine Net, April 25, 2020
Noninvasive, self-adhesive sensor predicted worsening heart failure in Veterans, EurekAlert, Feb. 25, 2020
VA doctors are using artificial intelligence to diagnose cancer, Military Times, Feb. 8, 2020
Alphabet’s AI might be able to predict kidney disease, Wired, July 31, 2019
Artificial intelligence diagnoses lung cancer, BBC News, May 20, 2019
In screening for suicide risk, Facebook takes on tricky public health role, The New York Times, Dec. 31, 2018
Electronic medication alerts designed with provider in mind reduce prescribing errors, Indiana University, March 25, 2017
Artificial intelligence is learning to predict and prevent suicide, WIRED, March 17, 2017
Online tool helps patients better understand EHR notes
Information Management, March 10, 2017
Genomic medicine goes mainstream, Modern Healthcare, Feb. 18, 2017
Eight years of decreased MRSA health care-associated infections associated with Veterans Affairs Prevention Initiative, Elsevier Health Sciences, Jan. 5, 2017
VA launches National Artificial Intelligence Institute, VA press release, Dec. 5, 2019
Artificial intelligence could help save kidneys, VA VAntage Point Blog, Aug. 30, 2019
VA aims to expand artificial-intelligence research, VA VAntage Point Blog, July 11, 2019
National Artificial Intelligence Institute, Department of Veterans Affairs, Office of Research and Development
Office of the National Coordinator for Health Information Technology, HealthIT.gov
Office of Health Informatics, U.S. Food and Drug Administration
Health Informatics, National Institutes of Health, National Library of Medicine
Introduction to Public Health Informatics, Centers for Disease Control and Prevention
Digital Healthcare Research: public health informatics, Agency for Healthcare Research and Quality
Health Communication and Health Information Technology, HealthyPeople.gov
VA launches National Artificial Intelligence Institute, VA press release, Dec. 5, 2019
Artificial intelligence could help save kidneys, VA VAntage Point Blog, Aug. 30, 2019
VA aims to expand artificial-intelligence research, VA VAntage Point Blog, July 11, 2019
National Artificial Intelligence Institute, Department of Veterans Affairs, Office of Research and Development
Office of the National Coordinator for Health Information Technology, HealthIT.gov
Office of Health Informatics, U.S. Food and Drug Administration
Health Informatics, National Institutes of Health, National Library of Medicine
Introduction to Public Health Informatics, Centers for Disease Control and Prevention
Digital Healthcare Research: public health informatics, Agency for Healthcare Research and Quality
Health Communication and Health Information Technology, HealthyPeople.gov